Abstract

Most ob ject tracking methods only exploit a single quanti- zation of an image space: pixels, superpixels, or bounding boxes, each of which has advantages and disadvantages. It is highly unlikely that a common optimal quantization level, suitable for tracking all ob jects in all environments, exists. We therefore propose a hierarchical appearance representation model for tracking, based on a graphical model that ex- ploits shared information across multiple quantization levels. The tracker aims to find the most possible position of the target by jointly classi- fying the pixels and superpixels and obtaining the best configuration across all levels. The motion of the bounding box is taken into consid- eration, while Online Random Forests are used to provide pixel- and superpixel-level quantizations and progressively updated on-the-fly. By appropriately considering the multilevel quantizations, our tracker ex- hibits not only excellent performance in non-rigid ob ject deformation handling, but also its robustness to occlusions. A quantitative evalua- tion is conducted on two benchmark datasets: a non-rigid ob ject tracking dataset (11 sequences) and the CVPR2013 tracking benchmark (50 se- quences). Experimental results show that our tracker overcomes various tracking challenges and is superior to a number of other popular tracking methods.